Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Contradiction Flagging · yogsoth-ai | DecimalAI

researchby yogsoth-ai

Contradiction Flagging

yogsoth-ai/contradiction-flagging

Source yogsoth-ai/de-anthropocentric-research-engine ↗License Apache-2.0

SOP for flagging contradictions in the causal model — identify conflicting evidence or mechanism claims.

NewMaintained

Automatic

Knowledge Management pack

Last verified 8/22/2026

What it changes

Passed 3 of 8 test cases with the skill, and 5 of 8 without it.

Without skill67%

With skill33%

Checks it passed that the model alone missed

Sets contradictions_found value to 2

1 fixed2 passed either way16 still failing3 broke

Pass-rate lift: -33 pp
Tokens: -21%
Agent turns: 0%
Response time: -40%

Model gemini-3.6-flashMeasured 8/22/2026v13 of 22 cases passed with skill · 8 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-contradiction-flagging/SKILL.md https://app.decimal.ai/s/yogsoth-ai-contradiction-flagging/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yogsoth-ai-contradiction-flagging, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/yogsoth-ai-contradiction-flagging/ and pins it in .decimal/skills.lock

decimalai skills add yogsoth-ai-contradiction-flagging

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-contradiction-flagging/SKILL.md https://app.decimal.ai/s/yogsoth-ai-contradiction-flagging/SKILL.md

Raw file: /s/yogsoth-ai-contradiction-flagging/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-contradiction-flagging.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

Evaluate `claims/revenue_projection_2025.md` against audit findings in `audits/q3_report.md`. If 2 distinct clashes are linked and recorded, how must the yield object reflect this count?

What was checked, without and with the skill
Checked	Without skill	With skill
Sets contradictions_found value to 2	Missed	Passed

case-18 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md25 linessingle file

Contradiction Flagging

Identify and flag contradictions: conflicting evidence, incompatible mechanisms, or circular reasoning.

Tool

vault_query_graph + vault_add_edge

Protocol

Query graph around a claim to find all evidence (supported_by and contradicts edges)
If both supporting and contradicting evidence exists, flag the contradiction
Create a contradicts edge between the conflicting items if not already present
Document the contradiction in a question page for resolution
Inline wikilinks: For each edge created, ensure the source page body contains [[dir/slug]] pointing to the target (dir/slug = target path minus .md). Place inline at semantically relevant location. Skip if already present.

HARD-GATE

Yield

Returns: { contradictions_found: number, documented: string[] }

Track record

Benchmark

3 / 8

test cases passed, vs 5 / 8 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

yogsoth-ai / de-anthropocentric-research-engine

skills/contradiction-flagging/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Contradiction Flagging

Tool

Protocol

HARD-GATE

Yield

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills